INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¿¯

-0.35

æĭĽ

-0.29

 soft

-0.27

 toString

-0.27

thon

-0.26

LOB

-0.25

è½¯

-0.25

 ster

-0.25

soft

-0.25

é¡½

-0.25

POSITIVE LOGITS

è®¸

0.28

 passionately

0.28

_perm

0.26

è¨±

0.26

nder

0.25

DeV

0.24

—he

0.23

ìľĦìĽĲíļĮ

0.23

-describedby

0.23

iffe

0.23

Activations Density 1.594%

No Known Activations

This feature has no known activations.